Nature Communications,2022年
Carmel Majidi, Mengmeng Sun, Shihao Yang, Bo Hao, Xin Wang, Li Zhang
LicenseType:CC BY |
| 
| 
[ 浏览：0 
下载：0
] Communications Biology,2022年
Hai-Qing Liu, Li Zhang, Allah Jurio Khaskheli, Guang-Qin Guo, Yu-Man Guo, Jun-Li Wang, Ya-Jie Zou, Qiong-Hui Fei, Peng Tian, Xiao-Feng Li, Lei Wu, Zuo-Xian Pu, Dong-Wei Di
LicenseType:CC BY |
3 Role of antiangiogenic agents in first-line treatment for advanced NSCLC in the era of immunotherapy [期刊论文]
BMC Cancer,2022年
Jia-Di Gan, Wen-Feng Fang, Jun Liao, Li Zhang, Lan-Lan Pang, Wael-Abdullah-Sultan Ali, Wei-Tao Zhuang, Yi-Hua Huang, Shao-Dong Hong
LicenseType:CC BY |
NPG Asia Materials,2022年
Renhou Han, Caofeng Pan, Xiaolong Feng, Li Zhang, Yepei Mo, Rongrong Bao
LicenseType:CC BY |
Nature Communications,2022年
Dekang Lv, Zhenzhen Li, Chanjun Sun, Xixi Duan, Yuanyuan Yang, Linyu Zhu, Chen Ni, Xiaohan Lou, Jialu Liang, Kaili Zhang, Linlin Wang, Li Zhang, Xiaohan Yao, Jiajia Wan, Ming Wang, Zhihai Qin
LicenseType:CC BY |
Computational Visual Media,2022年
Huiyuan Tian, Shijian Li, Min Yao, Gang Pan, Li Zhang
LicenseType:CC BY |
Significant progress has been made in image inpainting methods in recent years. However, they are incapable of producing inpainting results with reasonable structures, rich detail, and sharpness at the same time. In this paper, we propose the Pyramid-VAE-GAN network for image inpainting to address this limitation. Our network is built on a variational autoencoder (VAE) backbone that encodes high-level latent variables to represent complicated high-dimensional prior distributions of images. The prior assists in reconstructing reasonable structures when inpainting. We also adopt a pyramid structure in our model to maintain rich detail in low-level latent variables. To avoid the usual incompatibility of requiring both reasonable structures and rich detail, we propose a novel cross-layer latent variable transfer module. This transfers information about long-range structures contained in high-level latent variables to low-level latent variables representing more detailed information. We further use adversarial training to select the most reasonable results and to improve the sharpness of the images. Extensive experimental results on multiple datasets demonstrate the superiority of our method. Our code is available at https://github.com/thy960112/Pyramid-VAE-GAN.
878987797
028-85220240
